Improving Mathematical Reasoning Capabilities in Large Language Models via Reasoning Process Error Classification

arXiv:2609.15145v1 Announce Type: new Abstract: The reasoning ability of large language models (LLMs) is a critical factor for practical LLM-based applications. To investigate the current reasoning capability of LLMs, we clarify the types of errors that arise in LLMs' reasoning processes on mathematical datasets. We focus on problems where LLMs produce an incorrect answer. We define errors in the reasoning process as reasoning errors and manually analyze the features of reasoning errors. We defined and classified 21 error classes and identified the frequently occurring classes among them. Beyond qualitative evaluation, we leverage the evaluation results to improve the reasoning capability. We designed a prompt that explicitly focuses on eight error classes. The experiments demonstrate that this prompt effectively improves reasoning performance. Furthermore, the results suggest that the frequent reasoning errors identified in this paper are common across LLMs of comparable scale.

Related

• Disentangling Mathematical Reasoning in LLMs: A Methodological Investigation of Internal Mechanisms
• Scaling Reasoning Hop Exposes Weaknesses: Demystifying and Improving Hop Generalization in Large Language Models
• Process Supervision of Confidence Margin for Calibrated LLM Reasoning

Source: arXiv cs.CL | 2026-09-15